Somnus

Developers

Call Claude, GPT and Gemini from Next.js

In Next.js, call Somnus from a Route Handler or Server Action so the key stays on the server, and stream the reply back to your React UI.

Install

bash
npm install openai

Basic request

typescript
// app/api/chat/route.ts — runs on the server only
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.SOMNUS_API_KEY,
  baseURL: "https://gateway-production-c837.up.railway.app/v1",
});

export async function POST(req: Request) {
  const { message } = await req.json();
  const stream = await client.chat.completions.create({
    model: "claude-sonnet-5",
    messages: [{ role: "user", content: message }],
    stream: true,
  });
  const encoder = new TextEncoder();
  return new Response(new ReadableStream({
    async start(controller) {
      for await (const chunk of stream) {
        controller.enqueue(encoder.encode(chunk.choices[0]?.delta?.content ?? ""));
      }
      controller.close();
    },
  }));
}

Streaming

typescript
// app/api/chat/route.ts — runs on the server only
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.SOMNUS_API_KEY,
  baseURL: "https://gateway-production-c837.up.railway.app/v1",
});

export async function POST(req: Request) {
  const { message } = await req.json();
  const stream = await client.chat.completions.create({
    model: "claude-sonnet-5",
    messages: [{ role: "user", content: message }],
    stream: true,
  });
  const encoder = new TextEncoder();
  return new Response(new ReadableStream({
    async start(controller) {
      for await (const chunk of stream) {
        controller.enqueue(encoder.encode(chunk.choices[0]?.delta?.content ?? ""));
      }
      controller.close();
    },
  }));
}

JSON output

typescript
// app/api/chat/route.ts — runs on the server only
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.SOMNUS_API_KEY,
  baseURL: "https://gateway-production-c837.up.railway.app/v1",
});

export async function POST(req: Request) {
  const { message } = await req.json();
  const stream = await client.chat.completions.create({
    model: "claude-sonnet-5",
    messages: [{ role: "user", content: message }],
    stream: true,
  });
  const encoder = new TextEncoder();
  return new Response(new ReadableStream({
    async start(controller) {
      for await (const chunk of stream) {
        controller.enqueue(encoder.encode(chunk.choices[0]?.delta?.content ?? ""));
      }
      controller.close();
    },
  }));
}

Next.js notes

  • Keep SOMNUS_API_KEY in server-only environment variables (no NEXT_PUBLIC_ prefix).
  • Stream responses from a Route Handler for chat UIs.
  • Add per-user rate limits before going public.

Questions

Which models can I use?

Any of the 50+ models on Somnus — change the model string. The examples use claude-sonnet-5.

Where do I get a key?

Create an account, and your key appears in the dashboard with $5 of free credit.

Run this code with free credit

Create an account and get $5 of free API credit — enough to try every example on this page.

Get $5 free credit

Related

AI API for Go AI API for JavaScript (Node.js) Chatbots in Next.js with an AI API AI API for PHP AI API for Python AI API for REST (curl)

Browse more: Alternatives · Compare · Use cases · Developers · Solutions · Tools

WindowsStart with $5 free